runtime error

Exit code: 1. Reason: us code. To avoid downloading new versions of the code file, you can pin a revision. A new version of the following files was downloaded from https://huggingface.co/microsoft/Phi-3-vision-128k-instruct: - image_embedding_phi3_v.py . Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision. A new version of the following files was downloaded from https://huggingface.co/microsoft/Phi-3-vision-128k-instruct: - modeling_phi3_v.py - image_embedding_phi3_v.py . Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision. Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:12<00:12, 12.12s/it] Downloading shards: 100%|██████████| 2/2 [00:20<00:00, 9.74s/it] Downloading shards: 100%|██████████| 2/2 [00:20<00:00, 10.10s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 16, in <module> model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", trust_remote_code=True, torch_dtype="auto") File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 559, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4018, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1541, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1680, in _check_and_enable_flash_attn_2 raise ValueError( ValueError: FlashAttention2 has been toggled on, but it cannot be used due to the following error: Flash Attention 2 is not available on CPU. Please make sure torch can access a CUDA device.

Container logs: